BS
Bernt Schiele
cs.CVcs.LGcs.AIstat.MLcs.CRcs.CLAlgorithmscs.CYcs.SIeess.IV
On Valency
published · living versionsW_4wbseyw6·v1 · currentpublished
OneScene-Bench: Do Vision-Language Models Integrate Evidence Across Views?
with Swathi Suhas, Anurag Das, Jonas Fischer
1 version
W_av8u7vme·v1published
W_uwb2dfzx·v1published
Preprints & journals
254 papers in the corpus · 2004–2026PONDER: Learning to Generate in the Right Order2610.23531v1 · Julius Erbach, Dominik Narnhofer, Bernt Schiele et al.2026 · 0 citationsarXiv
DisParQ: Self-Supervised Part Concepts for Interpretable Vision Foundation Models2610.09802v1 · Adam Pardyl, Siddhartha Gairola, Sukrut Rao et al.2026 · 0 citationsarXiv
AnyBottle: A Recipe to Only Keep the Concepts You Really Need2610.08552v1 · Wolfgang Stammer, Sukrut Rao, Hevra Petekkaya et al.2026 · 0 citationsarXiv
Steering Fields: Adaptive Vector Fields for Safe Image Generation and Beyond2609.39573v1 · Simone Facchiano, Jan Eric Lenssen, Bernt Schiele et al.2026 · 0 citationsarXiv
TeMo: Temperature Modulation for Multimodal Contrastive Learning2609.07540v1 · Dhimitrios Duka, Bernt Schiele, Hilde Kuehne et al.2026 · 0 citationsarXiv
DataComp-VLM: Improved Open Datasets for Vision-Language Models2606.28551v3 · Matteo Farina, Vishaal Udandarao, Thao Nguyen et al.2026 · 0 citationsarXiv
TEVI: Text-Conditioned Editing of Visual Representations via Sparse Autoencoders for Improved Vision-Language Alignment2606.07451v2 · Sweta Mahajan, Sukrut Rao, Jiahao Xie et al.2026 · 0 citationsarXiv
Interpretability Without Tradeoffs: Disentangling Polysemanticity At Equal Predictive Performance2605.31304v1 · Dogukan Bagcı, Bernt Schiele, Simone Schaub-Meyer et al.2026 · 0 citationsarXiv
PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding2605.30126v1 · Selim Kuzucu, Alessio Tonioni, Vasile Lup et al.2026 · 0 citationsarXiv
R-CoV: Region-Aware Chain-of-Verification for Alleviating Object Hallucinations in LVLMs2604.20696v1 · Jiahao Xie, Alessio Tonioni, Nathalie Rauschmayr et al.2026 · 0 citationsarXiv
SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models2604.20705v1 · Jiahao Xie, Alessio Tonioni, Nathalie Rauschmayr et al.2026 · 0 citationsarXiv
Seeing Through Circuits: Faithful Mechanistic Interpretability for Vision Transformers2604.14477v1 · Nina Żukowska, Wolfgang Stammer, Bernt Schiele et al.2026 · 0 citationsarXiv
Do Instance Priors Help Weakly Supervised Semantic Segmentation?2604.11170v1 · Anurag Das, Anna Kukleva, Xinting Hu et al.2026 · 0 citationsarXiv
ClipTTT: CLIP-Guided Test-Time Training Helps LVLMs See Better2603.26486v1 · Mriganka Nath, Anurag Das, Jiahao Xie et al.2026 · 0 citationsarXiv
What Matters for Scalable and Robust Learning in End-to-End Driving Planners?2603.15185v1 · David Holtz, Niklas Hanselmann, Simon Doll et al.2026 · 0 citationsarXiv
What is Missing? Explaining Neurons Activated by Absent Concepts2603.09787v2 · Robin Hesse, Simone Schaub-Meyer, Janina Hesse et al.2026 · 0 citationsarXiv
MM-TS: Multi-Modal Temperature and Margin Schedules for Contrastive Learning with Long-Tail Data2603.08202v1 · Siarhei Sheludzko, Dhimitrios Duka, Bernt Schiele et al.2026 · 0 citationsarXiv
Rewis3d: Reconstruction Improves Weakly-Supervised Semantic Segmentation2603.06374v1 · Jonas Ernst, Wolfgang Boettcher, Lukas Hoyer et al.2026 · 1 citationarXiv
Certified Circuits: Stability Guarantees for Mechanistic Circuits2602.22968v3 · Alaa Anani, Tobias Lorenz, Bernt Schiele et al.2026 · 0 citationsarXiv
DAVE: Distribution-aware Attribution via ViT Gradient Decomposition2602.06613v1 · Adam Wr'obel, Siddhartha Gairola, Jacek Tabor et al.2026 · 0 citationsarXiv
CFM: Language-aligned Concept Foundation Model for Vision2601.13798v3 · Kai Wittenmayer, Sukrut Rao, Amin Parchami-Araghi et al.2026 · 0 citationsarXiv
More Images, More Problems? A Controlled Analysis of VLM Failure Modes2601.07812v1 · Anurag Das, Adrian Bulat, Alberto Baldrati et al.2026 · 0 citationsarXiv
Temporal Concept Dynamics in Diffusion Models via Prompt-Conditioned Interventions2512.08486v2 · Ada Gorgun, Fawaz Sammani, Nikos Deligiannis et al.2025 · 0 citationsarXiv
FaCT: Faithful Concept Traces for Explaining Neural Network Decisions2510.25512v2 · Amin Parchami-Araghi, Sukrut Rao, Jonas Fischer et al.2025 · 0 citationsarXiv
AnyUp: Universal Feature Upsampling2510.12764v2 · Thomas Wimmer, Prune Truong, Marie-Julie Rakotosaona et al.2025 · 1 citationarXiv
A Granular Study of Safety Pretraining under Model Abliteration2510.02768v1 · Shashank Agnihotri, Jonas Jakubassa, Priyam Dey et al.2025 · 0 citationsarXiv
RefAM: Attention Magnets for Zero-Shot Referral Segmentation2509.22650v3 · Anna Kukleva, Enis Simsar, Alessio Tonioni et al.2025 · 0 citationsTransactions on Machine Learning Research (2026)
AIM: Amending Inherent Interpretability via Self-Supervised Masking2508.11502v1 · Eyad Alshami, Shashank Agnihotri, Bernt Schiele et al.2025 · 2 citationsarXiv
Faithful, Interpretable Chest X-ray Diagnosis with Artifact-free B-cos Networks2507.16761v3 · Shreyash Arya, Shashank Agnihotri, Marcel Kleinmann et al.2025 · 0 citationsarXiv
Spatial Reasoners for Continuous Variables in Any Domain2507.10768v1 · Bart Pogodzinski, Christopher Wewer, Bernt Schiele et al.2025 · 0 citationsarXiv
LayerCake: Token-Aware Contrastive Decoding within Large Language Model Layers2507.04404v2 · Jingze Zhu, Yongliang Wu, Wenbo Zhu et al.2025 · 0 citationsarXiv
Enhancing Self-Supervised Visual Representation Learning via Low-Rank Adapted LLMs2507.00754v4 · Selim Kuzucu, Muhammad Ferjad Naeem, Anna Kukleva et al.2025 · 0 citationsarXiv
Pixel-level Certified Explanations via Randomized Smoothing2506.15499v1 · Alaa Anani, Tobias Lorenz, Mario Fritz et al.2025 · 0 citationsInternational Conference on Machine Learning (ICML), 2025
Solving Inverse Problems with FLAIR2506.02680v2 · Julius Erbach, Dominik Narnhofer, Andreas Dombos et al.2025 · 1 citationarXiv
KRIS-Bench: Benchmarking Next-Level Intelligent Image Editing Models2505.16707v1 · Yongliang Wu, Zonghui Li, Xinting Hu et al.2025 · 7 citationsarXiv
VITAL: More Understandable Feature Visualization through Distribution Alignment and Relevant Information Flow2503.22399v2 · Ada Gorgun, Bernt Schiele, Jonas Fischer2025 · 1 citationarXiv
Test-Time Visual In-Context Tuning2503.21777v1 · Jiahao Xie, Alessio Tonioni, Nathalie Rauschmayr et al.2025 · 1 citationarXiv
Unbiasing through Textual Descriptions: Mitigating Representation Bias in Video Benchmarks2503.18637v1 · Nina Shvetsova, Arsha Nagrani, Bernt Schiele et al.2025 · 4 citationsarXiv
Beyond Accuracy: What Matters in Designing Well-Behaved Image Classification Models?2503.17110v3 · Robin Hesse, Dogukan Bagcı, Bernt Schiele et al.2025 · 0 citationsarXiv
Interpretable 3D Neural Object Volumes for Robust Conceptual Reasoning2503.13429v2 · Nhi Pham, Artur Jesslen, Bernt Schiele et al.2025 · 0 citationsarXiv
How to Probe: Simple Yet Effective Techniques for Improving Post-hoc Explanations2503.00641v1 · Siddhartha Gairola, Moritz Bohle, Francesco Locatello et al.2025 · 0 citationsarXiv
Spatial Reasoning with Denoising Models2502.21075v2 · Christopher Wewer, Bart Pogodzinski, Bernt Schiele et al.2025 · 0 citationsarXiv
PersonaHOI: Effortlessly Improving Personalized Face with Human-Object Interaction Generation2501.05823v1 · Xinting Hu, Haoran Wang, Jan Eric Lenssen et al.2025 · 0 citationsarXiv
MEt3R: Measuring Multi-View Consistency in Generated Images2501.06336v2 · Mohammad Asim, Christopher Wewer, Thomas Wimmer et al.2025 · 33 citationsarXiv
Number it: Temporal Grounding Videos like Flipping Manga2411.10332v3 · Yongliang Wu, Xinting Hu, Yuyang Sun et al.2024 · 19 citationsarXiv
B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable2411.00715v2 · Shreyash Arya, Sukrut Rao, Moritz Bohle et al.2024 · 3 citationsarXiv
TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters2410.23168v2 · Haiyang Wang, Yue Fan, Muhammad Ferjad Naeem et al.2024 · 1 citationarXiv
Samba: Synchronized Set-of-Sequences Modeling for Multiple Object Tracking2410.01806v1 · Mattia Segu, Luigi Piccinelli, Siyuan Li et al.2024 · 1 citationarXiv
Walker: Self-supervised Multiple Object Tracking by Walking on Temporal Appearance Graphs2409.17221v1 · Mattia Segu, Luigi Piccinelli, Siyuan Li et al.2024 · 5 citationsarXiv
Scribbles for All: Benchmarking Scribble Supervised Segmentation Across Datasets2408.12489v1 · Wolfgang Boettcher, Lukas Hoyer, Ozan Unal et al.2024 · 4 citationsarXiv
Career total: at least 909 works. 254 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.